Pervasive Artificial Intelligence Research (PAIR) Labs

Drones and Computer Vision

Pervasive Artificial Intelligence Research (PAIR) Labs

Drones and Computer Vision

NCTU – Professor Yong-Sheng Chen

Co-principal investigator: Yong-Sheng Chen

Research :

Development of AI platform of Smart Drone ─ Intelligent Fight
Control / Prof. Jen-Hui Chuang

Core Technologies

Recent methods in monocular depth estimation either have an over-smoothing effect on object boundaries or carry large computational costs to estimate depth values. We present a fast, accurate, and lightweight convolutional neural network (CNN) to estimate monocular dense depth maps from a single image augmented with a sparse depth map and its mask. We conducted experiments on a variety of challenging datasets, where we achieve state-of-the-art performance in terms of accuracy, network model parameters, and speed.

Applications

Multi-view 3D scene reconstruction, depth estimation in autonomous driving

Technology Transfer

A fast and accurate sparse-to-dense network can automatically reconstructs depth estimation and 3D model from monocular RGB images and sparse depth information.

Technologies with Potential for Technology Transfer or Industry-Academia Collaboration

Multi-view stereo neural network can automatically reconstructs 3D scene model from multiple RGB images with different shooting angles.

Proposal for Industry-Academia Collaboration

A learning 3D geometry network can automatically reconstructs depth estimation and 3D model from monocular RGB images and sparse depth information.